© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3353
    Prev
    Next
    INDEX
    Explanations

    the word "veteran" followed by a numerical value between 9 and 10

    oai_token-act-pair · gpt-3.5-turbo

    references to veterans in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slow
    -0.87
    efficients
    -0.85
    alter
    -0.81
    perm
    -0.81
    matic
    -0.78
    laws
    -0.74
     lapt
    -0.74
    ammy
    -0.73
    ories
    -0.72
    apo
    -0.72
    POSITIVE LOGITS
     veteran
    1.18
     Veteran
    1.13
     veterans
    1.07
     vets
    0.96
    Veter
    0.91
     Veterans
    0.88
     vet
    0.82
     widow
    0.78
    TAIN
    0.69
     adventurer
    0.69
    Activations Density 0.010%

    No Known Activations